Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Berend Denkena
  • Marcel Wichmann
  • Markus Rokicki
  • Lukas Stürenburg
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seitenumfang10
FachzeitschriftProduction Engineering
Frühes Online-Datum9 Juli 2024
PublikationsstatusElektronisch veröffentlicht (E-Pub) - 9 Juli 2024

Abstract

The wear of cutting tools during milling processes not only constrains the volume of material that can be removed by a tool but also results in a progressive deterioration of the quality of the workpiece. Although there are established methodologies for predicting tool wear, there is a paucity of knowledge regarding the impact of tool wear on shape error. The authors present a data-driven soft sensor to model the effect of tool wear on shape error, obviating the need for direct tool wear measurement. To evaluate this approach, a milling experiment was conducted, wherein process forces, spindle current, and resulting shape error were measured. Furthermore, a geometrical cutting simulation was conducted in order to obtain cutting conditions, including the volume of material removed. This study examines the contribution of these features to the prediction performance of the proposed soft sensor. Additionally, the transferability from models trained on different tools is investigated to ascertain the impact of tool wear variance on prediction performance. Prediction experiments demonstrate that a soft-sensor based on a combination of simulation and process monitoring data enables a model trained on data from multiple milling tools to account for wear and predict shape error well under varying wear scenarios. The approach presented here has been demonstrated to result in a reduction of the prediction error of up to 60% compared to an average baseline prediction.

ASJC Scopus Sachgebiete

Zitieren

Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor. / Denkena, Berend; Wichmann, Marcel; Rokicki, Markus et al.
in: Production Engineering, 09.07.2024.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Denkena, B., Wichmann, M., Rokicki, M., & Stürenburg, L. (2024). Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor. Production Engineering. Vorabveröffentlichung online. https://doi.org/10.1007/s11740-024-01297-9
Denkena B, Wichmann M, Rokicki M, Stürenburg L. Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor. Production Engineering. 2024 Jul 9. Epub 2024 Jul 9. doi: 10.1007/s11740-024-01297-9
Denkena, Berend ; Wichmann, Marcel ; Rokicki, Markus et al. / Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor. in: Production Engineering. 2024.
Download
@article{696ca5d4295d42539d2e54db0023e040,
title = "Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor",
abstract = "The wear of cutting tools during milling processes not only constrains the volume of material that can be removed by a tool but also results in a progressive deterioration of the quality of the workpiece. Although there are established methodologies for predicting tool wear, there is a paucity of knowledge regarding the impact of tool wear on shape error. The authors present a data-driven soft sensor to model the effect of tool wear on shape error, obviating the need for direct tool wear measurement. To evaluate this approach, a milling experiment was conducted, wherein process forces, spindle current, and resulting shape error were measured. Furthermore, a geometrical cutting simulation was conducted in order to obtain cutting conditions, including the volume of material removed. This study examines the contribution of these features to the prediction performance of the proposed soft sensor. Additionally, the transferability from models trained on different tools is investigated to ascertain the impact of tool wear variance on prediction performance. Prediction experiments demonstrate that a soft-sensor based on a combination of simulation and process monitoring data enables a model trained on data from multiple milling tools to account for wear and predict shape error well under varying wear scenarios. The approach presented here has been demonstrated to result in a reduction of the prediction error of up to 60% compared to an average baseline prediction.",
keywords = "Machine learning, Milling, Soft sensor, Tool wear",
author = "Berend Denkena and Marcel Wichmann and Markus Rokicki and Lukas St{\"u}renburg",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",
year = "2024",
month = jul,
day = "9",
doi = "10.1007/s11740-024-01297-9",
language = "English",

}

Download

TY - JOUR

T1 - Modelling the influence of tool wear on shape errors in milling using a hybrid soft-sensor

AU - Denkena, Berend

AU - Wichmann, Marcel

AU - Rokicki, Markus

AU - Stürenburg, Lukas

N1 - Publisher Copyright: © The Author(s) 2024.

PY - 2024/7/9

Y1 - 2024/7/9

N2 - The wear of cutting tools during milling processes not only constrains the volume of material that can be removed by a tool but also results in a progressive deterioration of the quality of the workpiece. Although there are established methodologies for predicting tool wear, there is a paucity of knowledge regarding the impact of tool wear on shape error. The authors present a data-driven soft sensor to model the effect of tool wear on shape error, obviating the need for direct tool wear measurement. To evaluate this approach, a milling experiment was conducted, wherein process forces, spindle current, and resulting shape error were measured. Furthermore, a geometrical cutting simulation was conducted in order to obtain cutting conditions, including the volume of material removed. This study examines the contribution of these features to the prediction performance of the proposed soft sensor. Additionally, the transferability from models trained on different tools is investigated to ascertain the impact of tool wear variance on prediction performance. Prediction experiments demonstrate that a soft-sensor based on a combination of simulation and process monitoring data enables a model trained on data from multiple milling tools to account for wear and predict shape error well under varying wear scenarios. The approach presented here has been demonstrated to result in a reduction of the prediction error of up to 60% compared to an average baseline prediction.

AB - The wear of cutting tools during milling processes not only constrains the volume of material that can be removed by a tool but also results in a progressive deterioration of the quality of the workpiece. Although there are established methodologies for predicting tool wear, there is a paucity of knowledge regarding the impact of tool wear on shape error. The authors present a data-driven soft sensor to model the effect of tool wear on shape error, obviating the need for direct tool wear measurement. To evaluate this approach, a milling experiment was conducted, wherein process forces, spindle current, and resulting shape error were measured. Furthermore, a geometrical cutting simulation was conducted in order to obtain cutting conditions, including the volume of material removed. This study examines the contribution of these features to the prediction performance of the proposed soft sensor. Additionally, the transferability from models trained on different tools is investigated to ascertain the impact of tool wear variance on prediction performance. Prediction experiments demonstrate that a soft-sensor based on a combination of simulation and process monitoring data enables a model trained on data from multiple milling tools to account for wear and predict shape error well under varying wear scenarios. The approach presented here has been demonstrated to result in a reduction of the prediction error of up to 60% compared to an average baseline prediction.

KW - Machine learning

KW - Milling

KW - Soft sensor

KW - Tool wear

UR - http://www.scopus.com/inward/record.url?scp=85198099861&partnerID=8YFLogxK

U2 - 10.1007/s11740-024-01297-9

DO - 10.1007/s11740-024-01297-9

M3 - Article

AN - SCOPUS:85198099861

JO - Production Engineering

JF - Production Engineering

SN - 0944-6524

ER -